The research carried out in this project was overall kept within the boundaries of the original project plan. However, the HDPHMM framework byFox et al.
[2008] was not discovered before half way through the project period. This resulted in allocating time to understand and compare this framework to the IHMM, yielding less time for analysis on real-world data. It was agreed upon between the supervisors and the student that the statistical analysis and imple-mentation was the important part of this thesis, and therefore the physiological interpretation of the results was deemed out of scope of the thesis.
A general comment to the time schedule for the project is that it took much longer time than anticipated to implement the IHMM-MVAR model and val-idate the correctness of the code (both IHMM-MVAR and IHMM-Wish). This means that the actual time spent on different parts of the project was more in cycles (implement and validate, implement and validate,...) than the linear time table presented above.
Bibliography
David J Aldous.Exchangeability and related topics. Springer, 1985.
Elena A Allen, Eswar Damaraju, Sergey M Plis, Erik B Erhardt, Tom Eichele, and Vince D Calhoun. Tracking whole-brain connectivity dynamics in the resting state.Cerebral cortex, page bhs352, 2012.
Kasper Winther Andersen, Kristoffer H Madsen, Hartwig Roman Siebner, Mikkel N Schmidt, Morten Mørup, and Lars Kai Hansen. Non-parametric bayesian graph models reveal community structure in resting state fmri.
NeuroImage, 100:301–315, 2014.
Matthew J Beal, Zoubin Ghahramani, and Carl E Rasmussen. The infinite hid-den markov model. InAdvances in neural information processing systems, pages 577–584, 2001.
Christopher M Bishop et al. Pattern recognition and machine learning, volume 4.
springer New York, 2006.
David Blackwell and James B MacQueen. Ferguson distributions via pólya urn schemes. The annals of statistics, pages 353–355, 1973.
Randy L Buckner, Jorge Sepulcre, Tanveer Talukdar, Fenna M Krienen, Hes-heng Liu, Trey Hedden, Jessica R Andrews-Hanna, Reisa A Sperling, and Keith A Johnson. Cortical hubs revealed by intrinsic functional connectivity:
mapping, assessment of stability, and relation to alzheimer’s disease. The Journal of Neuroscience, 29(6):1860–1873, 2009.
VD Calhoun, T Adali, GD Pearlson, and JJ Pekar. A method for making group inferences from functional mri data using independent component analysis.
Human brain mapping, 14(3):140–151, 2001.
Vince D Calhoun, Tülay Adali, Lars Kai Hansen, Jan Larsen, and James J Pekar.
Ica of functional mri data: an overview. 2003.
Vince D Calhoun, Tom Eichele, and Godfrey Pearlson. Functional brain net-works in schizophrenia: a review. Frontiers in human neuroscience, 3, 2009.
Karen L Campbell, Omer Grigg, Cristina Saverino, Nathan Churchill, and Cheryl L Grady. Age differences in the intrinsic functional connectivity of default network subsystems.Frontiers in aging neuroscience, 5, 2013.
Catie Chang and Gary H Glover. Time–frequency dynamics of resting-state brain connectivity measured with fmri. Neuroimage, 50(1):81–98, 2010.
Jeff H Duyn. Eeg-fmri methods for the study of brain networks during sleep.
Frontiers in neurology, 3, 2012.
Emily B Fox. Bayesian nonparametric learning of complex dynamical phenomena.
PhD thesis, Massachusetts Institute of Technology, 2009.
Emily B Fox, Erik B Sudderth, Michael I Jordan, and Alan S Willsky. An hdp-hmm for systems with state persistence. InProceedings of the 25th international conference on Machine learning, pages 312–319. ACM, 2008.
Karl J Friston. Functional and effective connectivity: a review. Brain connectiv-ity, 1(1):13–36, 2011.
Karl J Friston, Lee Harrison, and Will Penny. Dynamic causal modelling. Neu-roimage, 19(4):1273–1302, 2003.
Rainer Goebel, Alard Roebroeck, Dae-Shik Kim, and Elia Formisano. Investi-gating directed cortical interactions in time-resolved fmri data using vector autoregressive modeling and granger causality mapping.Magnetic resonance imaging, 21(10):1251–1261, 2003.
C Gössl, L Fahrmeir, and DP Auer. Bayesian modeling of the hemodynamic response function in bold fmri.Neuroimage, 14(1):140–148, 2001.
Michael D Greicius, Gaurav Srivastava, Allan L Reiss, and Vinod Menon.
Default-mode network activity distinguishes alzheimer’s disease from healthy aging: evidence from functional mri. Proceedings of the National Academy of Sciences of the United States of America, 101(13):4637–4642, 2004.
Roger B Grosse and David K Duvenaud. Testing mcmc code. arXiv preprint arXiv:1412.5218, 2014.
L Harrison, William D Penny, and Karl Friston. Multivariate autoregressive modeling of fmri time series. NeuroImage, 19(4):1477–1491, 2003.
W Keith Hastings. Monte carlo sampling methods using markov chains and their applications.Biometrika, 57(1):97–109, 1970.
BIBLIOGRAPHY 83
Michael C Hughes, Erik B Sudderth, and Emily B Fox. Effective split-merge monte carlo methods for nonparametric models of sequential data. In Ad-vances in Neural Information Processing Systems, pages 1295–1303, 2012.
Human Connectome Project. WU-Minn HCP 500 Subjects + MEG2 Data Re-lease: Reference Manual. http://humanconnectome.org/documentation/
S500/HCP_S500+MEG2_Release_Reference_Manual.pdf, 2014. [Online; ac-cessed 02-May-2015].
R Matthew Hutchison, Thilo Womelsdorf, Elena A Allen, Peter A Bandettini, Vince D Calhoun, Maurizio Corbetta, Stefania Della Penna, Jeff H Duyn, Gary H Glover, Javier Gonzalez-Castillo, et al. Dynamic functional connec-tivity: promise, issues, and interpretations. Neuroimage, 80:360–378, 2013.
Sonia Jain and Radford M Neal. A split-merge markov chain monte carlo pro-cedure for the dirichlet process mixture model. Journal of Computational and Graphical Statistics, 13(1), 2004.
Gebhard Kirchgässner, Jürgen Wolters, and Uwe Hassler.Introduction to modern time series analysis. Springer Science & Business Media, 2012.
Vesa Kiviniemi, Tapani Vire, Jukka Remes, Ahmed Abou Elseoud, Tuomo Starck, Osmo Tervonen, and Juha Nikkinen. A sliding time-window ica re-veals spatial variability of the default mode network in time.Brain connectiv-ity, 1(4):339–347, 2011.
Josefine Korzen, Kristoffer H Madsen, and Morten Mørup. Quantifying tem-poral states in rs-fmri data using bayesian nonparametrics. In HBM 2014.
Organization for Human Brain Mapping, 2014.
Kenneth K Kwong, John W Belliveau, David A Chesler, Inna E Goldberg, Robert M Weisskoff, Brigitte P Poncelet, David N Kennedy, Bernice E Hop-pel, Mark S Cohen, and Robert Turner. Dynamic magnetic resonance imag-ing of human brain activity durimag-ing primary sensory stimulation.Proceedings of the National Academy of Sciences, 89(12):5675–5679, 1992.
Xiao Liu and Jeff H Duyn. Time-varying functional network information ex-tracted from brief instances of spontaneous brain activity. Proceedings of the National Academy of Sciences, 110(11):4392–4397, 2013.
Torben E Lund, Kristoffer H Madsen, Karam Sidaros, Wen-Lin Luo, and Thomas E Nichols. Non-white noise in fmri: does modelling have an im-pact? Neuroimage, 29(1):54–66, 2006.
Waqas Majeed, Matthew Magnuson, Wendy Hasenkamp, Hillary Schwarb, Eric H Schumacher, Lawrence Barsalou, and Shella D Keilholz. Spatiotem-poral dynamics of low frequency bold fluctuations in rats and humans. Neu-roimage, 54(2):1140–1150, 2011.
Nicholas Metropolis and Stanislaw Ulam. The monte carlo method. Journal of the American statistical association, 44(247):335–341, 1949.
Radford M Neal. Probabilistic inference using markov chain monte carlo meth-ods. 1993.
Seiji Ogawa, David W Tank, Ravi Menon, Jutta M Ellermann, Seong G Kim, Helmut Merkle, and Kamil Ugurbil. Intrinsic signal changes accompany-ing sensory stimulation: functional brain mappaccompany-ing with magnetic resonance imaging. Proceedings of the National Academy of Sciences, 89(13):5951–5955, 1992.
Roger Penrose. A generalized inverse for matrices. InMathematical proceedings of the Cambridge philosophical society, volume 51, pages 406–413. Cambridge Univ Press, 1955.
David B Phillips and Adrian FM Smith. Bayesian model comparison via jump diffusions. InMarkov chain Monte Carlo in practice, pages 215–239. Springer, 1996.
Jim Pitman. Poisson–dirichlet and gem invariant distributions for split-and-merge transformations of an interval partition. Combinatorics, Probability &
Computing, 11(05):501–514, 2002.
Lawrence Rabiner. A tutorial on hidden markov models and selected applica-tions in speech recognition. Proceedings of the IEEE, 77(2):257–286, 1989.
Marcus E Raichle, Ann Mary MacLeod, Abraham Z Snyder, William J Powers, Debra A Gusnard, and Gordon L Shulman. A default mode of brain function.
Proceedings of the National Academy of Sciences, 98(2):676–682, 2001.
Peter M Rasmussen, Lars K Hansen, Kristoffer H Madsen, Nathan W Churchill, and Stephen C Strother. Model sparsity and brain pattern interpretation of classification models in neuroimaging. Pattern Recognition, 45(6):2085–2100, 2012.
Marieke L Schölvinck, Alexander Maier, Q Ye Frank, Jeff H Duyn, and David A Leopold. Neural basis of global resting-state fmri activity. Proceedings of the National Academy of Sciences, 107(22):10238–10243, 2010.
J. Sethuraman. A constructive definition of Dirichlet priors. Statistica Sinica, 4:
639–650, 1994.
Anne M Smith, Bobbi K Lewis, Urs E Ruttimann, Q Ye Frank, Teresa M Sin-nwell, Yihong Yang, Jeff H Duyn, and Joseph A Frank. Investigation of low frequency drift in fmri signal.Neuroimage, 9(5):526–533, 1999.
BIBLIOGRAPHY 85
Kerri Smith. Brain imaging: fmri 2.0. Nature News, 2012. URLhttp://www.
nature.com/news/brain-imaging-fmri-2-0-1.10365.
Klaas Enno Stephan and Alard Roebroeck. A short history of causal modeling of fmri data.Neuroimage, 62(2):856–863, 2012.
Christoph Stippich et al. Clinical functional MRI. Springer, 2007.
Enzo Tagliazucchi, Pablo Balenzuela, Daniel Fraiman, and Dante Chialvo. Crit-icality in large-scale brain fmri dynamics unveiled by a novel point process analysis. Frontiers in Physiology, 3(15), 2012.
Yee Whye Teh, Michael I Jordan, Matthew J Beal, and David M Blei. Hierarchi-cal dirichlet processes. Journal of the american statistical association, 101(476), 2006.
Garth John Thompson, Matthew Evan Magnuson, Michael Donelyn Merritt, Hillary Schwarb, Wen-Ju Pan, Andrew McKinley, Lloyd D Tripp, Eric H Schumacher, and Shella Dawn Keilholz. Short-time windows of correlation between large-scale functional brain networks predict vigilance intraindivid-ually and interindividintraindivid-ually. Human brain mapping, 34(12):3280–3298, 2013.
David C Van Essen, Kamil Ugurbil, E Auerbach, D Barch, TEJ Behrens, R Bu-cholz, A Chang, Liyong Chen, Maurizio Corbetta, Sandra W Curtiss, et al.
The human connectome project: a data acquisition perspective. Neuroimage, 62(4):2222–2231, 2012.
J. Van Gael. The infinite hidden markov model, 2010. http://mloss.org/
software/view/205/.
Jurgen Van Gael. Bayesian Nonparametric Hidden Markov Models. PhD thesis, University of Cambridge, 2012.
Alan S Willsky, Erik B Sudderth, Michael I Jordan, and Emily B Fox. Nonpara-metric bayesian learning of switching linear dynamical systems. InAdvances in Neural Information Processing Systems, pages 457–464, 2009.
Qingbao Yu, Erik B Erhardt, Jing Sui, Yuhui Du, Hao He, Devon Hjelm, Mustafa S Cetin, Srinivas Rachakonda, Robyn L Miller, Godfrey Pearlson, et al. Assessing dynamic brain graphs of time-varying connectivity in fmri data: Application to healthy controls and patients with schizophrenia. Neu-roImage, 107:345–355, 2015.
Andrew Zalesky, Alex Fornito, Luca Cocchi, Leonardo L Gollo, and Michael Breakspear. Time-resolved resting-state brain networks. Proceedings of the National Academy of Sciences, 111(28):10341–10346, 2014.